Duration Control With Variable Length Synthesis

via “duration control with variable-length synthesis”

Latent diffusion model for generating music and sound effects from text.

Unique: Implements duration control through temporal conditioning in the diffusion model rather than post-processing or concatenation, enabling seamless variable-length generation without artifacts. The model learns to scale temporal structure based on requested duration during training.

vs others: More flexible than fixed-length generators (which produce only 30-second or 60-second audio) because duration is user-controllable, and higher quality than concatenation-based approaches because the full audio is generated coherently in a single pass.

via “variable-length video generation with adaptive temporal scheduling”

text-to-video model by undefined. 89,853 downloads.

Unique: Uses temporal positional encoding that generalizes across sequence lengths, enabling the same model weights to generate videos of 5-30 frames without fine-tuning or model switching. Implements adaptive temporal scheduling that adjusts diffusion steps based on target length, optimizing inference cost for shorter videos.

vs others: More flexible than fixed-length competitors (e.g., Stable Video Diffusion which generates fixed 4-second clips); avoids the computational overhead of maintaining separate models for different video lengths.

via “variable-length video generation with adaptive temporal modeling”

text-to-video model by undefined. 16,568 downloads.

Unique: Uses learnable temporal positional embeddings that interpolate or extrapolate based on target frame count, enabling a single model to generate videos of 2-8 seconds without retraining. This contrasts with fixed-length models (e.g., Stable Video Diffusion) that require separate checkpoints per duration or post-hoc frame interpolation.

vs others: More efficient than frame interpolation-based approaches (which require 2-3x inference passes) because temporal adaptation is built into the model, and more flexible than fixed-length competitors because duration is a runtime parameter rather than a training-time constraint.

via “variable-length video generation with duration control”

An image-to-video and text-to-video model developed by Niobotics ByteDance.

Unique: Implements temporal positional encoding that dynamically scales based on requested duration, allowing the diffusion model to learn duration-aware motion patterns during training and adapt motion speed at inference time without retraining

vs others: More efficient than frame interpolation approaches for variable-length generation because it generates the correct number of frames directly rather than generating fixed-length videos and then interpolating or dropping frames